Instructions to use buerokratt/ner_gdpr with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use buerokratt/ner_gdpr with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="buerokratt/ner_gdpr")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("buerokratt/ner_gdpr") model = AutoModelForTokenClassification.from_pretrained("buerokratt/ner_gdpr", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download predict_results.json from buerokratt/ner_gdpr: direct link, hf CLI and curl.
- Browser
- Download file 2.35 kB
-
https://huggingface.co/buerokratt/ner_gdpr/resolve/main/predict_results.json
- Command line
-
hf download hf://buerokratt/ner_gdpr/predict_results.json
-
curl -L -o predict_results.json https://huggingface.co/buerokratt/ner_gdpr/resolve/main/predict_results.json
2.35 kB
| { | |
| "predict_DATE_f1": 0.9586466165413534, | |
| "predict_DATE_number": 263, | |
| "predict_DATE_precision": 0.9479553903345725, | |
| "predict_DATE_recall": 0.9695817490494296, | |
| "predict_EVENT_f1": 0.675, | |
| "predict_EVENT_number": 43, | |
| "predict_EVENT_precision": 0.7297297297297297, | |
| "predict_EVENT_recall": 0.627906976744186, | |
| "predict_GPE_f1": 0.9226319595083153, | |
| "predict_GPE_number": 710, | |
| "predict_GPE_precision": 0.9479940564635958, | |
| "predict_GPE_recall": 0.8985915492957747, | |
| "predict_LOC_f1": 0.8223350253807107, | |
| "predict_LOC_number": 96, | |
| "predict_LOC_precision": 0.801980198019802, | |
| "predict_LOC_recall": 0.84375, | |
| "predict_MONEY_f1": 0.9905362776025236, | |
| "predict_MONEY_number": 158, | |
| "predict_MONEY_precision": 0.9874213836477987, | |
| "predict_MONEY_recall": 0.9936708860759493, | |
| "predict_ORG_f1": 0.9243085880640466, | |
| "predict_ORG_number": 691, | |
| "predict_ORG_precision": 0.9297218155197657, | |
| "predict_ORG_recall": 0.918958031837916, | |
| "predict_PERCENT_f1": 1.0, | |
| "predict_PERCENT_number": 59, | |
| "predict_PERCENT_precision": 1.0, | |
| "predict_PERCENT_recall": 1.0, | |
| "predict_PER_f1": 0.945721271393643, | |
| "predict_PER_number": 1020, | |
| "predict_PER_precision": 0.9434146341463414, | |
| "predict_PER_recall": 0.9480392156862745, | |
| "predict_PROD_f1": 0.7830985915492958, | |
| "predict_PROD_number": 183, | |
| "predict_PROD_precision": 0.8081395348837209, | |
| "predict_PROD_recall": 0.7595628415300546, | |
| "predict_TIME_f1": 0.9166666666666666, | |
| "predict_TIME_number": 36, | |
| "predict_TIME_precision": 0.9166666666666666, | |
| "predict_TIME_recall": 0.9166666666666666, | |
| "predict_TITLE_f1": 0.9275929549902153, | |
| "predict_TITLE_number": 260, | |
| "predict_TITLE_precision": 0.9442231075697212, | |
| "predict_TITLE_recall": 0.9115384615384615, | |
| "predict_accuracy": 0.9876867318727783, | |
| "predict_f1": 0.9243986254295533, | |
| "predict_loss": 0.09665972739458084, | |
| "predict_overall_accuracy": 0.9876867318727783, | |
| "predict_overall_f1": 0.9243986254295533, | |
| "predict_overall_precision": 0.9316017316017317, | |
| "predict_overall_recall": 0.9173060528559249, | |
| "predict_precision": 0.9316017316017317, | |
| "predict_recall": 0.9173060528559249, | |
| "predict_runtime": 8.3917, | |
| "predict_samples_per_second": 333.304, | |
| "predict_steps_per_second": 10.487 | |
| } |